Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to physical objects made of metal

    oai_token-act-pair · gpt-3.5-turbo

    the verb "is"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stakes
    -0.62
     allotted
    -0.59
     thumbnail
    -0.55
     downt
    -0.54
     hours
    -0.54
    ¥ŀ
    -0.53
     hectares
    -0.53
     MFT
    -0.52
    ruciating
    -0.52
     galleries
    -0.52
    POSITIVE LOGITS
    abeth
    1.38
    terness
    1.07
    aunder
    1.02
    kell
    1.01
    ystem
    1.01
    ciplinary
    1.00
    ection
    0.99
    heng
    0.99
    rael
    0.98
    por
    0.97
    Act Density 0.055%

    No Known Activations